INDEX

Explanations

structured data or code snippets related to digital content

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hentet

-0.70

:+:

-0.66

">//

-0.64

contentLoaded

-0.64

LookAnd

-0.63

aarrggbb

-0.62

IsMutable

-0.62

Sucesor

-0.62

Jereo

-0.61

RectangleBorder

-0.60

POSITIVE LOGITS

cellona

0.63

afone

0.60

lgari

0.56

anthene

0.56

ophon

0.54

벳

0.52

onaceous

0.52

ölker

0.51

BOUR

0.51

migrationBuilder

0.51

Activations Density 0.093%

structured data or code snippets related to digital content

No Comments

No Known Activations